This model has some serious quality issues. It's not broken and still chat but it significantly underperforms the original model on complicated tasks.

This is LFM2.5-1.2B-Thinking quantized with llm-compressor to NVFP4. The model is compatible with vLLM (tested: v0.14.0). Tested with an L4 (Google Colab).

Downloads last month
59
Safetensors
Model size
0.9B params
Tensor type
F32
BF16
F8_E4M3
U8
Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support

Model tree for kaitchup/LFM2.5-1.2B-Thinking-NVFP4

Quantized
(23)
this model